typos

apache · Jul 29, 2014 · bd2df13 · bd2df13
1 parent 07ddff2
commit bd2df13
Show file tree

Hide file tree

Showing 3 changed files with 48 additions and 46 deletions.
diff --git a/mllib/src/main/scala/org/apache/spark/mllib/api/python/PythonMLLibAPI.scala b/mllib/src/main/scala/org/apache/spark/mllib/api/python/PythonMLLibAPI.scala
@@ -516,7 +516,8 @@ class PythonMLLibAPI extends Serializable {
   /**
    * Java stub for Python mllib RandomRDDGenerators.poissonVectorRDD()
    */
-  def poissonVectorRDD(jsc: JavaSparkContext,mean: Double,
+  def poissonVectorRDD(jsc: JavaSparkContext,
+      mean: Double,
       numRows: Long,
       numCols: Int,
       numPartitions: Int,

diff --git a/mllib/src/main/scala/org/apache/spark/mllib/random/RandomRDDGenerators.scala b/mllib/src/main/scala/org/apache/spark/mllib/random/RandomRDDGenerators.scala
@@ -26,17 +26,17 @@ import org.apache.spark.util.Utils
 
 /**
  * :: Experimental ::
- * Generator methods for creating RDDs comprised of i.i.d samples from some distribution.
+ * Generator methods for creating RDDs comprised of i.i.d. samples from some distribution.
  */
 @Experimental
 object RandomRDDGenerators {
 
   /**
    * :: Experimental ::
-   * Generates an RDD comprised of i.i.d samples from the uniform distribution on [0.0, 1.0].
+   * Generates an RDD comprised of i.i.d. samples from the uniform distribution on [0.0, 1.0].
    *
    * To transform the distribution in the generated RDD from U[0.0, 1.0] to U[a, b], use
-   * `RandomRDDGenerators.uniformRDD(sc, n, p, seed).map(v => (b - a) * v)`
+   * `RandomRDDGenerators.uniformRDD(sc, n, p, seed).map(v => a + (b - a) * v)`.
    *
    * @param sc SparkContext used to create the RDD.
    * @param size Size of the RDD.
@@ -52,10 +52,10 @@ object RandomRDDGenerators {
 
   /**
    * :: Experimental ::
-   * Generates an RDD comprised of i.i.d samples from the uniform distribution on [0.0, 1.0].
+   * Generates an RDD comprised of i.i.d. samples from the uniform distribution on [0.0, 1.0].
    *
    * To transform the distribution in the generated RDD from U[0.0, 1.0] to U[a, b], use
-   * `RandomRDDGenerators.uniformRDD(sc, n, p).map(v => (b - a) * v)`
+   * `RandomRDDGenerators.uniformRDD(sc, n, p).map(v => a + (b - a) * v)`.
    *
    * @param sc SparkContext used to create the RDD.
    * @param size Size of the RDD.
@@ -69,11 +69,11 @@ object RandomRDDGenerators {
 
   /**
    * :: Experimental ::
-   * Generates an RDD comprised of i.i.d samples from the uniform distribution on [0.0, 1.0].
+   * Generates an RDD comprised of i.i.d. samples from the uniform distribution on [0.0, 1.0].
    * sc.defaultParallelism used for the number of partitions in the RDD.
    *
    * To transform the distribution in the generated RDD from U[0.0, 1.0] to U[a, b], use
-   * `RandomRDDGenerators.uniformRDD(sc, n).map(v => (b - a) * v)`
+   * `RandomRDDGenerators.uniformRDD(sc, n).map(v => a + (b - a) * v)`.
    *
    * @param sc SparkContext used to create the RDD.
    * @param size Size of the RDD.
@@ -86,10 +86,10 @@ object RandomRDDGenerators {
 
   /**
    * :: Experimental ::
-   * Generates an RDD comprised of i.i.d samples from the standard normal distribution.
+   * Generates an RDD comprised of i.i.d. samples from the standard normal distribution.
    *
    * To transform the distribution in the generated RDD from standard normal to some other normal
-   * N(mean, sigma), use `RandomRDDGenerators.normalRDD(sc, n, p, seed).map(v => mean + sigma * v)`
+   * N(mean, sigma), use `RandomRDDGenerators.normalRDD(sc, n, p, seed).map(v => mean + sigma * v)`.
    *
    * @param sc SparkContext used to create the RDD.
    * @param size Size of the RDD.
@@ -105,10 +105,10 @@ object RandomRDDGenerators {
 
   /**
    * :: Experimental ::
-   * Generates an RDD comprised of i.i.d samples from the standard normal distribution.
+   * Generates an RDD comprised of i.i.d. samples from the standard normal distribution.
    *
    * To transform the distribution in the generated RDD from standard normal to some other normal
-   * N(mean, sigma), use `RandomRDDGenerators.normalRDD(sc, n, p).map(v => mean + sigma * v)`
+   * N(mean, sigma), use `RandomRDDGenerators.normalRDD(sc, n, p).map(v => mean + sigma * v)`.
    *
    * @param sc SparkContext used to create the RDD.
    * @param size Size of the RDD.
@@ -122,11 +122,11 @@ object RandomRDDGenerators {
 
   /**
    * :: Experimental ::
-   * Generates an RDD comprised of i.i.d samples from the standard normal distribution.
+   * Generates an RDD comprised of i.i.d. samples from the standard normal distribution.
    * sc.defaultParallelism used for the number of partitions in the RDD.
    *
    * To transform the distribution in the generated RDD from standard normal to some other normal
-   * N(mean, sigma), use `RandomRDDGenerators.normalRDD(sc, n).map(v => mean + sigma * v)`
+   * N(mean, sigma), use `RandomRDDGenerators.normalRDD(sc, n).map(v => mean + sigma * v)`.
    *
    * @param sc SparkContext used to create the RDD.
    * @param size Size of the RDD.
@@ -139,7 +139,7 @@ object RandomRDDGenerators {
 
   /**
    * :: Experimental ::
-   * Generates an RDD comprised of i.i.d samples from the Poisson distribution with the input mean.
+   * Generates an RDD comprised of i.i.d. samples from the Poisson distribution with the input mean.
    *
    * @param sc SparkContext used to create the RDD.
    * @param mean Mean, or lambda, for the Poisson distribution.
@@ -160,7 +160,7 @@ object RandomRDDGenerators {
 
   /**
    * :: Experimental ::
-   * Generates an RDD comprised of i.i.d samples from the Poisson distribution with the input mean.
+   * Generates an RDD comprised of i.i.d. samples from the Poisson distribution with the input mean.
    *
    * @param sc SparkContext used to create the RDD.
    * @param mean Mean, or lambda, for the Poisson distribution.
@@ -175,7 +175,7 @@ object RandomRDDGenerators {
 
   /**
    * :: Experimental ::
-   * Generates an RDD comprised of i.i.d samples from the Poisson distribution with the input mean.
+   * Generates an RDD comprised of i.i.d. samples from the Poisson distribution with the input mean.
    * sc.defaultParallelism used for the number of partitions in the RDD.
    *
    * @param sc SparkContext used to create the RDD.
@@ -190,7 +190,7 @@ object RandomRDDGenerators {
 
   /**
    * :: Experimental ::
-   * Generates an RDD comprised of i.i.d samples produced by the input DistributionGenerator.
+   * Generates an RDD comprised of i.i.d. samples produced by the input DistributionGenerator.
    *
    * @param sc SparkContext used to create the RDD.
    * @param generator DistributionGenerator used to populate the RDD.
@@ -210,7 +210,7 @@ object RandomRDDGenerators {
 
   /**
    * :: Experimental ::
-   * Generates an RDD comprised of i.i.d samples produced by the input DistributionGenerator.
+   * Generates an RDD comprised of i.i.d. samples produced by the input DistributionGenerator.
    *
    * @param sc SparkContext used to create the RDD.
    * @param generator DistributionGenerator used to populate the RDD.
@@ -228,7 +228,7 @@ object RandomRDDGenerators {
 
   /**
    * :: Experimental ::
-   * Generates an RDD comprised of i.i.d samples produced by the input DistributionGenerator.
+   * Generates an RDD comprised of i.i.d. samples produced by the input DistributionGenerator.
    * sc.defaultParallelism used for the number of partitions in the RDD.
    *
    * @param sc SparkContext used to create the RDD.
@@ -247,7 +247,7 @@ object RandomRDDGenerators {
 
   /**
    * :: Experimental ::
-   * Generates an RDD[Vector] with vectors containing i.i.d samples drawn from the
+   * Generates an RDD[Vector] with vectors containing i.i.d. samples drawn from the
    * uniform distribution on [0.0 1.0].
    *
    * @param sc SparkContext used to create the RDD.
@@ -269,14 +269,14 @@ object RandomRDDGenerators {
 
   /**
    * :: Experimental ::
-   * Generates an RDD[Vector] with vectors containing i.i.d samples drawn from the
+   * Generates an RDD[Vector] with vectors containing i.i.d. samples drawn from the
    * uniform distribution on [0.0 1.0].
    *
    * @param sc SparkContext used to create the RDD.
    * @param numRows Number of Vectors in the RDD.
    * @param numCols Number of elements in each Vector.
    * @param numPartitions Number of partitions in the RDD.
-   * @return RDD[Vector] with vectors containing i.i.d samples ~ U[0.0, 1.0].
+   * @return RDD[Vector] with vectors containing i.i.d. samples ~ U[0.0, 1.0].
    */
   @Experimental
   def uniformVectorRDD(sc: SparkContext,
@@ -288,14 +288,14 @@ object RandomRDDGenerators {
 
   /**
    * :: Experimental ::
-   * Generates an RDD[Vector] with vectors containing i.i.d samples drawn from the
+   * Generates an RDD[Vector] with vectors containing i.i.d. samples drawn from the
    * uniform distribution on [0.0 1.0].
    * sc.defaultParallelism used for the number of partitions in the RDD.
    *
    * @param sc SparkContext used to create the RDD.
    * @param numRows Number of Vectors in the RDD.
    * @param numCols Number of elements in each Vector.
-   * @return RDD[Vector] with vectors containing i.i.d samples ~ U[0.0, 1.0].
+   * @return RDD[Vector] with vectors containing i.i.d. samples ~ U[0.0, 1.0].
    */
   @Experimental
   def uniformVectorRDD(sc: SparkContext, numRows: Long, numCols: Int): RDD[Vector] = {
@@ -304,15 +304,15 @@ object RandomRDDGenerators {
 
   /**
    * :: Experimental ::
-   * Generates an RDD[Vector] with vectors containing i.i.d samples drawn from the
+   * Generates an RDD[Vector] with vectors containing i.i.d. samples drawn from the
    * standard normal distribution.
    *
    * @param sc SparkContext used to create the RDD.
    * @param numRows Number of Vectors in the RDD.
    * @param numCols Number of elements in each Vector.
    * @param numPartitions Number of partitions in the RDD.
    * @param seed Seed for the RNG that generates the seed for the generator in each partition.
-   * @return RDD[Vector] with vectors containing i.i.d samples ~ N(0.0, 1.0).
+   * @return RDD[Vector] with vectors containing i.i.d. samples ~ N(0.0, 1.0).
    */
   @Experimental
   def normalVectorRDD(sc: SparkContext,
@@ -326,14 +326,14 @@ object RandomRDDGenerators {
 
   /**
    * :: Experimental ::
-   * Generates an RDD[Vector] with vectors containing i.i.d samples drawn from the
+   * Generates an RDD[Vector] with vectors containing i.i.d. samples drawn from the
    * standard normal distribution.
    *
    * @param sc SparkContext used to create the RDD.
    * @param numRows Number of Vectors in the RDD.
    * @param numCols Number of elements in each Vector.
    * @param numPartitions Number of partitions in the RDD.
-   * @return RDD[Vector] with vectors containing i.i.d samples ~ N(0.0, 1.0).
+   * @return RDD[Vector] with vectors containing i.i.d. samples ~ N(0.0, 1.0).
    */
   @Experimental
   def normalVectorRDD(sc: SparkContext,
@@ -345,14 +345,14 @@ object RandomRDDGenerators {
 
   /**
    * :: Experimental ::
-   * Generates an RDD[Vector] with vectors containing i.i.d samples drawn from the
+   * Generates an RDD[Vector] with vectors containing i.i.d. samples drawn from the
    * standard normal distribution.
    * sc.defaultParallelism used for the number of partitions in the RDD.
    *
    * @param sc SparkContext used to create the RDD.
    * @param numRows Number of Vectors in the RDD.
    * @param numCols Number of elements in each Vector.
-   * @return RDD[Vector] with vectors containing i.i.d samples ~ N(0.0, 1.0).
+   * @return RDD[Vector] with vectors containing i.i.d. samples ~ N(0.0, 1.0).
    */
   @Experimental
   def normalVectorRDD(sc: SparkContext, numRows: Long, numCols: Int): RDD[Vector] = {
@@ -361,7 +361,7 @@ object RandomRDDGenerators {
 
   /**
    * :: Experimental ::
-   * Generates an RDD[Vector] with vectors containing i.i.d samples drawn from the
+   * Generates an RDD[Vector] with vectors containing i.i.d. samples drawn from the
    * Poisson distribution with the input mean.
    *
    * @param sc SparkContext used to create the RDD.
@@ -370,7 +370,7 @@ object RandomRDDGenerators {
    * @param numCols Number of elements in each Vector.
    * @param numPartitions Number of partitions in the RDD.
    * @param seed Seed for the RNG that generates the seed for the generator in each partition.
-   * @return RDD[Vector] with vectors containing i.i.d samples ~ Pois(mean).
+   * @return RDD[Vector] with vectors containing i.i.d. samples ~ Pois(mean).
    */
   @Experimental
   def poissonVectorRDD(sc: SparkContext,
@@ -385,15 +385,15 @@ object RandomRDDGenerators {
 
   /**
    * :: Experimental ::
-   * Generates an RDD[Vector] with vectors containing i.i.d samples drawn from the
+   * Generates an RDD[Vector] with vectors containing i.i.d. samples drawn from the
    * Poisson distribution with the input mean.
    *
    * @param sc SparkContext used to create the RDD.
    * @param mean Mean, or lambda, for the Poisson distribution.
    * @param numRows Number of Vectors in the RDD.
    * @param numCols Number of elements in each Vector.
    * @param numPartitions Number of partitions in the RDD.
-   * @return RDD[Vector] with vectors containing i.i.d samples ~ Pois(mean).
+   * @return RDD[Vector] with vectors containing i.i.d. samples ~ Pois(mean).
    */
   @Experimental
   def poissonVectorRDD(sc: SparkContext,
@@ -406,15 +406,15 @@ object RandomRDDGenerators {
 
   /**
    * :: Experimental ::
-   * Generates an RDD[Vector] with vectors containing i.i.d samples drawn from the
+   * Generates an RDD[Vector] with vectors containing i.i.d. samples drawn from the
    * Poisson distribution with the input mean.
    * sc.defaultParallelism used for the number of partitions in the RDD.
    *
    * @param sc SparkContext used to create the RDD.
    * @param mean Mean, or lambda, for the Poisson distribution.
    * @param numRows Number of Vectors in the RDD.
    * @param numCols Number of elements in each Vector.
-   * @return RDD[Vector] with vectors containing i.i.d samples ~ Pois(mean).
+   * @return RDD[Vector] with vectors containing i.i.d. samples ~ Pois(mean).
    */
   @Experimental
   def poissonVectorRDD(sc: SparkContext,
@@ -426,7 +426,7 @@ object RandomRDDGenerators {
 
   /**
    * :: Experimental ::
-   * Generates an RDD[Vector] with vectors containing i.i.d samples produced by the
+   * Generates an RDD[Vector] with vectors containing i.i.d. samples produced by the
    * input DistributionGenerator.
    *
    * @param sc SparkContext used to create the RDD.
@@ -435,7 +435,7 @@ object RandomRDDGenerators {
    * @param numCols Number of elements in each Vector.
    * @param numPartitions Number of partitions in the RDD.
    * @param seed Seed for the RNG that generates the seed for the generator in each partition.
-   * @return RDD[Vector] with vectors containing i.i.d samples produced by generator.
+   * @return RDD[Vector] with vectors containing i.i.d. samples produced by generator.
    */
   @Experimental
   def randomVectorRDD(sc: SparkContext,
@@ -449,15 +449,15 @@ object RandomRDDGenerators {
 
   /**
    * :: Experimental ::
-   * Generates an RDD[Vector] with vectors containing i.i.d samples produced by the
+   * Generates an RDD[Vector] with vectors containing i.i.d. samples produced by the
    * input DistributionGenerator.
    *
    * @param sc SparkContext used to create the RDD.
    * @param generator DistributionGenerator used to populate the RDD.
    * @param numRows Number of Vectors in the RDD.
    * @param numCols Number of elements in each Vector.
    * @param numPartitions Number of partitions in the RDD.
-   * @return RDD[Vector] with vectors containing i.i.d samples produced by generator.
+   * @return RDD[Vector] with vectors containing i.i.d. samples produced by generator.
    */
   @Experimental
   def randomVectorRDD(sc: SparkContext,
@@ -470,15 +470,15 @@ object RandomRDDGenerators {
 
   /**
    * :: Experimental ::
-   * Generates an RDD[Vector] with vectors containing i.i.d samples produced by the
+   * Generates an RDD[Vector] with vectors containing i.i.d. samples produced by the
    * input DistributionGenerator.
    * sc.defaultParallelism used for the number of partitions in the RDD.
    *
    * @param sc SparkContext used to create the RDD.
    * @param generator DistributionGenerator used to populate the RDD.
    * @param numRows Number of Vectors in the RDD.
    * @param numCols Number of elements in each Vector.
-   * @return RDD[Vector] with vectors containing i.i.d samples produced by generator.
+   * @return RDD[Vector] with vectors containing i.i.d. samples produced by generator.
    */
   @Experimental
   def randomVectorRDD(sc: SparkContext,

diff --git a/python/pyspark/mllib/randomRDD.py b/python/pyspark/mllib/randomRDD.py
@@ -20,7 +20,6 @@
 from pyspark.rdd import RDD
 from pyspark.mllib._common import _deserialize_double, _deserialize_double_vector
 from pyspark.serializers import NoOpSerializer
-from pyspark.statcounter import StatCounter
 
 class RandomRDDGenerators:
     """
@@ -31,12 +30,12 @@ class RandomRDDGenerators:
     @staticmethod
     def uniformRDD(sc, size, numPartitions=None, seed=None):
         """
-        Generates an RDD comprised of i.i.d samples from the
+        Generates an RDD comprised of i.i.d. samples from the
         uniform distribution on [0.0, 1.0].
 
         To transform the distribution in the generated RDD from U[0.0, 1.0]
         to U[a, b], use
-        C{RandomRDDGenerators.uniformRDD(sc, n, p, seed).map(lambda v: (b - a) * v)}
+        C{RandomRDDGenerators.uniformRDD(sc, n, p, seed).map(lambda v: a + (b - a) * v)}
 
         >>> x = RandomRDDGenerators.uniformRDD(sc, 100).collect()
         >>> len(x)
@@ -65,6 +64,7 @@ def normalRDD(sc, size, numPartitions=None, seed=None):
         C{RandomRDDGenerators.normal(sc, n, p, seed).map(lambda v: mean + sigma * v)}
 
         >>> x = RandomRDDGenerators.normalRDD(sc, 1000, seed=1L).collect()
+        >>> from pyspark.statcounter import StatCounter
         >>> stats = StatCounter(x)
         >>> stats.count()
         1000L
@@ -86,6 +86,7 @@ def poissonRDD(sc, mean, size, numPartitions=None, seed=None):
 
         >>> mean = 100.0
         >>> x = RandomRDDGenerators.poissonRDD(sc, mean, 1000, seed=1L).collect()
+        >>> from pyspark.statcounter import StatCounter
         >>> stats = StatCounter(x)
         >>> stats.count()
         1000L